List disputes via GET /v1/customer/disputes. Filter by disputed_transaction_id, dispute_state, update_time_before / update_time_after. Pagination via page_size and next_page_token.
AI agents call list_disputes to retrieve information from Mcp Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves dispute records with query filters and pagination—a read-only operation with no side effects. While the context involves financial disputes (relevant to AP2 payment protocol), the tool itself merely queries and returns dispute data without modifying records or committing financial actions. The GET verb and filtering parameters confirm retrieval-only functionality.
From the tool's definition Tool uses GET method to list disputes with filtering and pagination parameters. Description explicitly states 'List disputes via GET /v1/customer/disputes' with filter and pagination options.
Documented attack patterns abuse exactly the kind of access list_disputes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for list_disputes:
{
"version": "1",
"default": "deny",
"tools": {
"list_disputes": {}
}
}list_disputes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List disputes via GET /v1/customer/disputes. Filter by disputed_transaction_id, dispute_state, update_time_before / update_time_after. Pagination via page_size and next_page_token. It is categorised as a Read tool in the Mcp Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for list_disputes: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Ap2. Nothing to install.
list_disputes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_disputes rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_disputes. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_disputes is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.